On 06/28/2012 08:56 AM, Andrea Arcangeli wrote:
Add the config options to allow building the kernel with AutoNUMA. If CONFIG_AUTONUMA_DEFAULT_ENABLED is "=y", then /sys/kernel/mm/autonuma/enabled will be equal to 1, and AutoNUMA will be enabled automatically at boot. CONFIG_AUTONUMA currently depends on X86, because no other arch implements the pte/pmd_numa yet and selecting =y would result in a failed build, but this shall be relaxed in the future. Porting AutoNUMA to other archs should be pretty simple. Signed-off-by: Andrea Arcangeli<aarcange@xxxxxxxxxx>
The Makefile changes could be merged into this patch
diff --git a/mm/Kconfig b/mm/Kconfig index 82fed4e..330dd51 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -207,6 +207,19 @@ config MIGRATION pages as migration can relocate pages to satisfy a huge page allocation instead of reclaiming. +config AUTONUMA + bool "Auto NUMA" + select MIGRATION + depends on NUMA&& X86
How about having the x86 architecture export a HAVE_AUTONUMA flag, and testing for that?
+ help + Automatic NUMA CPU scheduling and memory migration.
This could be expanded to list advantages and disadvantages of having autonuma enabled. -- All rights reversed -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>